Notion Schedule Agent
An MCP server that turns your Notion task list into an AI-optimized daily schedule, reading tasks with page content and priorities from an Eisenhower matrix, and writing a clean schedule back to Notion.
README
Notion Schedule Agent
An MCP server that turns your Notion task list into an AI-optimized daily schedule.
Every night you pull tomorrow's tasks from your "Upcoming Tasks" database and manually slot them into half-hour blocks. This agent does that for you — it reads your tasks (including page body content like workout plans and watchlists), understands priorities via the Eisenhower matrix, respects fixed-time commitments parsed from task names, and writes a clean schedule back to Notion.
Demo
1. Tasks in Notion with Eisenhower priorities and weekday assignments

2. The agent reads full page content for smarter scheduling

3. One command generates an AI-optimized daily schedule

4. Schedule written back to Notion as a half-hour block table

5. Built as an MCP server — usable from Claude Desktop, Cursor, or any MCP client

How It Works
┌──────────────────┐ ┌──────────────────┐ ┌──────────────────┐
│ Upcoming Tasks │──────▶│ AI Scheduler │──────▶│ Schedule Today │
│ (Notion DB) │ │ (OpenAI) │ │ (Notion Table) │
│ │ │ │ │ │
│ • Task name │ │ • Reads page │ │ 6:00 Free time │
│ • Priority │ │ body content │ │ 9:00 LeetCode │
│ • Weekday │ │ • Parses times │ │ 9:30 Standup │
│ • Page content │ │ • Sorts by │ │ 10:00 Deep work │
│ │ │ priority │ │ ... │
└──────────────────┘ └──────────────────┘ └──────────────────┘
Priority System (Eisenhower Matrix)
| Status | Meaning | Scheduling |
|---|---|---|
Imp Urg |
Important & Urgent | Peak focus hours first |
Urg ~Imp |
Urgent, not important | Soon, lighter slots |
Imp ~Urg |
Important, not urgent | Focused time available |
In Progress |
Currently being worked on | Dedicated blocks |
~Imp ~Urg |
Neither important nor urgent | Fill remaining gaps |
Pinned |
Recurring/daily tasks | Spread across the day |
Key Features
- Deep content reading — reads the body of each task page (bullet lists, paragraphs) so the AI understands what "Gym - upper body" actually involves
- Time-locked tasks — parses times from task names (e.g. "Team standup 9:30am") and locks them to the correct slot
- Eisenhower priority — schedules Important & Urgent tasks in peak focus hours, lighter tasks in the evening
- Two-step workflow — preview the schedule before writing it to Notion
- MCP server — any MCP client can invoke
plan_day,get_tasks, andapply_schedule
Setup
1. Install dependencies
pip install -r requirements.txt
2. Create a Notion Integration
- Go to notion.so/my-integrations
- Click New integration, give it a name (e.g. "Schedule Agent")
- Copy the Internal Integration Secret — this is your
NOTION_API_KEY
3. Share your Notion pages with the integration
- Open your Upcoming Tasks database in Notion
- Click ... → Connections → select your integration
- Do the same for your Getting Things Done page (the one with "Schedule Today")
4. Get your database and page IDs
-
Open Upcoming Tasks in Notion. The URL looks like:
https://notion.so/workspace/YOUR_DB_ID?v=...Copy the 32-character hex ID. -
Open Getting Things Done page. Same format — copy the page ID.
5. Configure environment
cp .env.example .env
Edit .env with your keys:
NOTION_API_KEY=ntn_your_key_here
OPENAI_API_KEY=sk-your_key_here
NOTION_TASKS_DB_ID=your_database_id
NOTION_SCHEDULE_PAGE_ID=your_page_id
Usage
CLI Mode
# List tomorrow's tasks
python -m src.cli tasks tomorrow
# Generate and apply a schedule for tomorrow
python -m src.cli plan tomorrow
# Plan a specific day
python -m src.cli plan monday
The plan command shows a preview and asks for confirmation before writing to Notion.
MCP Server Mode
Run the server for use with Claude Desktop, Cursor, or any MCP client:
python -m src.mcp_server
Claude Desktop configuration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"notion-schedule-agent": {
"command": "python",
"args": ["-m", "src.mcp_server"],
"cwd": "/path/to/notion-mcp-v2",
"env": {
"NOTION_API_KEY": "ntn_...",
"OPENAI_API_KEY": "sk-...",
"NOTION_TASKS_DB_ID": "...",
"NOTION_SCHEDULE_PAGE_ID": "..."
}
}
}
}
Available MCP Tools
| Tool | Description |
|---|---|
get_tasks(day) |
List tasks for a given day from Notion |
plan_day(day) |
Generate an AI-optimized schedule (preview) |
apply_schedule() |
Write the previewed schedule to Notion |
day accepts "today", "tomorrow", or a weekday name like "Monday".
Tech Stack
- Python — core language
- Notion API via
notion-client— reads task database + page content, writes schedule table - OpenAI (
gpt-4o-mini) — intelligent scheduling with priority awareness - MCP (Model Context Protocol) via
mcpSDK — exposes tools to any MCP client
Project Structure
src/
config.py — environment config, time slots, priority mapping
notion_ops.py — Notion API operations (read tasks + page content, write schedule)
scheduler.py — OpenAI-powered schedule generation
mcp_server.py — MCP server entry point with tool definitions
cli.py — standalone CLI for direct usage
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.